Hostname: page-component-7b9c58cd5d-nzzs5 Total loading time: 0 Render date: 2025-03-13T15:19:42.541Z Has data issue: false hasContentIssue false
  • English
  • Français

Development of automatic surveillance of animal behaviour and welfare using image analysis and machine learned segmentation technique

Published online by Cambridge University Press:  20 July 2015

M. Nilsson ,
A. H. Herlin ,
H. Ardö ,
O. Guzhva ,
K. Åström  and
C. Bergsten
M. Nilsson
Affiliation:
Lund University, Centre for Mathematical Sciences, PO Box 118, SE-22100 Lund, Sweden
A. H. Herlin*
Affiliation:
Swedish University of Agricultural Sciences, Department of Biosystems and Technology, PO Box 103, SE-23053 Alnarp, Sweden
H. Ardö
Affiliation:
Lund University, Centre for Mathematical Sciences, PO Box 118, SE-22100 Lund, Sweden
O. Guzhva
Affiliation:
Swedish University of Agricultural Sciences, Department of Biosystems and Technology, PO Box 103, SE-23053 Alnarp, Sweden
K. Åström
Affiliation:
Lund University, Centre for Mathematical Sciences, PO Box 118, SE-22100 Lund, Sweden
C. Bergsten
Affiliation:
Swedish University of Agricultural Sciences, Department of Biosystems and Technology, PO Box 103, SE-23053 Alnarp, Sweden
*
†E-mail: anders.herlin@slu.se
Get access

Abstract

In this paper the feasibility to extract the proportion of pigs located in different areas of a pig pen by advanced image analysis technique is explored and discussed for possible applications. For example, pigs generally locate themselves in the wet dunging area at high ambient temperatures in order to avoid heat stress, as wetting the body surface is the major path to dissipate the heat by evaporation. Thus, the portion of pigs in the dunging area and resting area, respectively, could be used as an indicator of failure of controlling the climate in the pig environment as pigs are not supposed to rest in the dunging area. The computer vision methodology utilizes a learning based segmentation approach using several features extracted from the image. The learning based approach applied is based on extended state-of-the-art features in combination with a structured prediction framework based on a logistic regression solver using elastic net regularization. In addition, the method is able to produce a probability per pixel rather than form a hard decision. This overcomes some of the limitations found in a setup using grey-scale information only. The pig pen is a difficult imaging environment because of challenging lighting conditions like shadows, poor lighting and poor contrast between pig and background. In order to test practical conditions, a pen containing nine young pigs was filmed from a top view perspective by an Axis M3006 camera with a resolution of 640×480 in three, 10-min sessions under different lighting conditions. The results indicate that a learning based method improves, in comparison with greyscale methods, the possibility to reliable identify proportions of pigs in different areas of the pen. Pigs with a changed behaviour (location) in the pen may indicate changed climate conditions. Changed individual behaviour may also indicate inferior health or acute illness.

Keywords

behaviour analysisimage segmentationratio of areaspigs
Type
Research Article
Information
animal , Volume 9 , Issue 11 , November 2015 , pp. 1859 - 1865
Copyright
© The Animal Consortium 2015 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Aarnink, AJA, Schrama, JW, Heetkamp, MJW, Stefanowska, J and Huynh, TTT 2006. Temperature and body weight affect fouling of pig pens. Journal of Animal Science 84, 2224–2231.Google Scholar
Berckmans, D 2004. Automatic on-line monitoring of animals by precision livestock farming. In Proceedings of the ISAH Conference on Animal Production in Europe: The Way Forward in a Changing World. October 11–13, Saint-Malo, France, vol. 1 pp. 27–31.Google Scholar
Botermans, J and Andersson, M 1995. Growing-finishing pigs in an uninsulated house. 2. Pen function and thermal comfort. Swedish Journal of Agricultural Research 25, 83–92.Google Scholar
Dollár, P, Appel, R, Belongie, S and Perona, P 2014. Fast feature pyramids for object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 36, 1532–1545.Google Scholar
Dollár, P, Belongie, S and Perona, P 2010. The fastest pedestrian detector in the west. BMVC Proceedings of the British Machine Vision Conference, August 31–September 3, Aberystwyth, UK.Google Scholar
Ekesbo, I 2011. Farm animal behaviour: characteristics for assessment of health and welfare. Cabi International, Wallingford, UK.Google Scholar
Hacker, RR, Ogilvie, JR, Morrison, WD and Kains, F 1994. Factors affecting excretory behavior of pigs. Journal of Animal Science 72, 1455–1460.Google Scholar
Hoff, SJ, Janni, KA and Jacobson, LD 1992. Three dimensional buoyant turbulent flows in a scaled model, slot-ventilated, livestock confinement facility. Transactions of the ASAE 35, 671–686.Google Scholar
Horsted, K, Kongsted, AG, Jørgensen, U and Sørensen, J 2012. Combined production of free-range pigs and energy crops – animal behaviour and crop damages. Livestock Science 150, 200–208.Google Scholar
Kashiha, M, Pluk, A, Bahr, C, Vranken, E and Berckmans, D 2013. Development of an early warning system for a broiler house using computer vision. Biosystems Engineering 116, 36–45.Google Scholar
Kashiha, MA, Bahr, C, Ott, S, Moons, CP, Niewold, TA, Tuyttens, F and Berckmans, D 2014. Automatic monitoring of pig locomotion using image analysis. Livestock Science 159, 141–148.CrossRefGoogle Scholar
Mul, M, Vermeij, I, Hindle, V and Spoolder, H 2010. EU-welfare legislation on pigs, Report 273, March. Wageningen UR, Livestock Research, 34.Google Scholar
Nilsson, M 2014. Elastic net regularized logistic regression using cubic majorization. 22nd International Conference on Pattern Recognition (ICPR 2014), Stockholm, Sweden, August 24–28.Google Scholar
Nilsson, M, Ardö, H, Åström, K, Herlin, A, Bergsten, C and Guzhva, O 2014. Learning based image segmentation of pigs in a pen. Visual observation and analysis of vertebrate and insect behavior – Workshop at the 22nd International Conference on Pattern Recognition (ICPR 2014), Stockholm, Sweden, August 24–28.Google Scholar
Oczak, M, Ismayilova, G, Costa, A, Viazzi, S, Thays Sonoda, L, Fels, M, Bahr, C, Hartung, J, Guarino, M, Berckmans, D and Vranken, E 2013. Analysis of aggressive behaviours of pigs by automatic video recordings. Computers and Electronics in Agriculture 99, 209–217.CrossRefGoogle Scholar
Otsu, N 1979. A threshold selection method from gray level histograms. IEEE Transactions, Systems, Man and Cybernetics 9, 62–66.CrossRefGoogle Scholar
Ott, S, Moons, C, Kashiha, M, Bahr, C, Tuyttens, F, Berckmans, D and Niewold, T 2014. Automated video analysis of pig activity at pen level highly correlates to human observations of behavioural activities. Livestock Science 160, 132–137.CrossRefGoogle Scholar
Shao, B and Xin, H 2008. A real-time computer vision assessment and control of thermal comfort for group-housed pigs. Computers and Electronics in Agriculture 62, 15–21.Google Scholar
Van Wagenberg, AV, Aerts, JM, Van Brecht, A, Vranken, E, Leroy, T and Berckmans, D 2005. Climate control based on temperature measurement in the animal-occupied zone of a pig room with ground channel ventilation. Transactions of the ASAE 48, 355–365.Google Scholar
Wechsler, B 1996. Rearing pigs in species-specific family groups. Animal Welfare 5, 25–35.Google Scholar